Nutlope/llamatutor

An AI personal tutor built with Llama 3.1

What it solves

This project provides an open-source AI personal tutor that helps you get on-demand answers to questions. It combines a large language model with web search so you can receive responses that can reflect current information, making it a handy tool for learning or quick reference.

How it works

It uses Meta's Llama 3.1 70B model as the core language engine, with Together AI handling the actual inference call. For queries that benefit from fresh or detailed online content, it integrates the Exa search API. The front end is built with Next.js (App Router) and Tailwind CSS, while Helicone provides observability and Plausible handles website analytics. To run it yourself, you clone the repo, sign up for Together AI, Exa, and Helicone, add your API keys to a .env file, and run npm install and npm run dev.

Who it’s for

It’s aimed at anyone who wants an AI tutor they can run themselves—students, self-learners, or developers interested in customizing an open-source learning assistant. Because it’s open source, you can adapt it to your own needs.

Highlights

  • Powered by Meta’s Llama 3.1 70B model
  • Uses Together AI for efficient inference
  • Integrates Exa for web search to fetch relevant results
  • Built with Next.js and Tailwind CSS for a modern UI
  • Includes observability via Helicone and analytics via Plausible
  • Easy to set up locally with a simple clone-and-run process

Related

  • Project
    AI-in-Health/MedLLMsPracticalGuide

    A comprehensive, curated guide to the development and application of Large Language Models in medicine, providing researchers and developers with a structured roadmap of methodologies, datasets, and clinical use cases.

  • Project
    shcherbak-ai/contextgem

    ContextGem is an open‑source Python library for extracting structured, typed facts from documents using LLMs and low‑cost decision models. You declare aspects (text sections) and concepts (typed values) in plain language; the library auto‑generates prompts, routes each extraction to the appropriate model, validates output, and returns each fact with its source paragraph and optional justification. It supports probability‑based answers from decision models, batch processing, and full documentation.

  • Project
    CaviraOSS/PageLM

    PageLM is an open-source AI education platform that converts documents and lecture notes into interactive study tools like quizzes, flashcards, and AI-generated podcasts.

  • Project
    aceliuchanghong/FAQ_Of_LLM_Interview

    A curated collection of interview questions and conceptual study guides for candidates preparing for Large Language Model algorithm engineering roles.